writing-plans

Converts specs into detailed multi-step implementation plans with TDD tasks.

Updated May 4, 2026
One-click install
npx skills add https://github.com/Ab0umar/selrs.cc --skill writing-plans-ab0umar
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: writing-plans
Source: https://github.com/Ab0umar/selrs.cc/tree/main/.codex/plugins/cache/openai-curated/superpowers/dc902811/skills/writing-plans
Command: npx skills add https://github.com/Ab0umar/selrs.cc --skill writing-plans-ab0umar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Engineers often start coding from a spec without a clear roadmap, leading to missed requirements, inconsistent structure, and rework. This Skill turns a spec or requirements document into a complete, bite-sized implementation plan that an engineer with zero codebase context can follow. ## Core Features & Use Cases - Structured Plan Generation: Produces a plan document with a required header, file structure mapping, and tasks broken into 2-5 minute steps following TDD (failing test, run, implement, verify, commit). - Quality Guardrails: Enforces exact file paths, complete code in every step, exact commands with expected output, and bans placeholders like TODO or "add error handling". - Self-Review and Handoff: Includes a self-review checklist for spec coverage, placeholder scans, and type consistency, plus an execution handoff offering subagent-driven or inline execution. - Use Case: Given a feature spec for a new API endpoint, generate a dated plan file in docs/superpowers/plans/ with checkbox-tracked tasks that a subagent can execute one by one. ## Quick Start Ask the agent to use the writing-plans skill to create an implementation plan from your spec document before writing any code.

Frequently Asked Questions about writing-plans

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write an implementation plan from a spec before coding?

Provide your spec or requirements document and invoke the writing-plans skill. It produces a plan with a goal, architecture summary, file structure map, and tasks broken into 2-5 minute steps following a test-first cycle, saved to docs/superpowers/plans/.

What makes a good implementation plan for AI coding agents?

A good plan assumes zero codebase context: exact file paths, complete code in every step, exact commands with expected output, and no placeholders like TODO. Each task should be self-contained so an agent can execute tasks independently or out of order.

How granular should tasks be in a coding implementation plan?

Each step should be one action taking 2-5 minutes: write the failing test, run it to confirm failure, implement minimal code, run tests to confirm passing, then commit. This granularity keeps verification tight and errors easy to isolate.

When should a spec be split into multiple implementation plans?

Split when the spec covers multiple independent subsystems. Each plan should produce working, testable software on its own. The skill's scope check recommends separate plans per subsystem rather than one monolithic plan.

How are completed plans executed after writing?

After saving the plan, you choose between subagent-driven execution, which dispatches a fresh subagent per task with review between tasks, or inline execution, which runs tasks in batches with checkpoints in the current session.